Presentation | 2023-11-05 Investigation of Effective Features for Estimating Agreement or Disagreement by Facial images in Online Conferences Hiroki Saito, Kyotaro Sato, Junji Yamato, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In online conferences, it is more difficult to capture detailed facial expression changes than in offline conferences. In addition, it is difficult to convey the intentions of the participants. In this study, we investigate effective features f or estimating agreement and disagreement using facial images. We confirm whether grouping people with similar facial expression changes is effective in estimating agreement or disagreement by grouping people with similar facial expression changes and comparing the resul ts with those without grouping. As a result of feature selection based on feature importance using XGBoost, the estimation accuracy was improved by making individual binary classifiers for groups prone to changes around the eyes and groups prone to changes around the mouth, rather than making a binary classifier using all the data without grouping. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Online Conferences / Agreement / Disagreement / Facial expression recognition |
Paper # | CNR2023-15,HCS2023-77 |
Date of Issue | 2023-10-29 (CNR, HCS) |
Conference Information | |
Committee | HCS / CNR |
---|---|
Conference Date | 2023/11/5(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Kogakuin University |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Communication and Interaction of Human, Robot, and Agent, etc. |
Chair | Tomoko Kanda(Osaka Inst. of Tech.) / Yuri Nishikawa(AIST) |
Vice Chair | Sachiko Takagi(Tokiwa Univ.) / Masashi Komori(Osaka Electro-Comm. Univ.) / Junji Yamato(Kogakuin Univ.) |
Secretary | Sachiko Takagi(Ritsumeikan Univ.) / Masashi Komori(Kanagawa Univ.) / Junji Yamato(Shizuoka Univ.) |
Assistant | HUANG HUNGHSUAN(Univ. of Fukuchiyama) / Jun Ichikawa(Shizuoka Univ.) / Kazuki Takashima(Tohoku Univ.) / Hiroto Saito(Tokyo Denki Univ.) / Ryo Ishii(NTT) / Yuka Kobayashi(Toshiba) / Yoshihiko Murakawa(Teikyo Heisei Univ.) |
Paper Information | |
Registration To | Technical Committee on Human Communication Science / Technical Committee on Cloud Network Robotics |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Investigation of Effective Features for Estimating Agreement or Disagreement by Facial images in Online Conferences |
Sub Title (in English) | |
Keyword(1) | Online Conferences |
Keyword(2) | Agreement |
Keyword(3) | Disagreement |
Keyword(4) | Facial expression recognition |
1st Author's Name | Hiroki Saito |
1st Author's Affiliation | Kogakuin University(Kogakuin Univ.) |
2nd Author's Name | Kyotaro Sato |
2nd Author's Affiliation | Kogakuin University(Kogakuin Univ.) |
3rd Author's Name | Junji Yamato |
3rd Author's Affiliation | Kogakuin University(Kogakuin Univ.) |
Date | 2023-11-05 |
Paper # | CNR2023-15,HCS2023-77 |
Volume (vol) | vol.123 |
Number (no) | CNR-241,HCS-242 |
Page | pp.pp.45-49(CNR), pp.45-49(HCS), |
#Pages | 5 |
Date of Issue | 2023-10-29 (CNR, HCS) |